核心信息
T-Mem 是一个开源记忆架构（EMNLP 2026），据称是首个覆盖“联想回忆”能力的方案，突破了多数记忆系统仅靠相似度检索的局限。
要点
- 写入记忆时附带“触发器”，相当于提前预测这条记忆未来何时会再次有用。
- 查询时根据情境触发并召回相关记忆，即使与查询没有关键词重叠也能命中。
- 作为架构层设计，无需微调即可接入任意大语言模型。
T-Mem：一种预测记忆何时重要的开源记忆架构
原始推文
This might be the first open-source memory architecture to cover associative recall. The rest stop at similarity search. (T-Mem, EMNLP 2026) Most memory systems retrieve by similarity. T-Mem predicts when a memory will matter, before you ask. → write: memories ship with a trigger at store time, basically "when will this come up again?" → read: at query time, triggers pull in memories by situation, even with zero keyword overlap. → architecture layer. plugs into any LLM without fine-tuning or model changes. On LoCoMo-Plus (strips keyword overlap, tests pure associative recall), mainstream systems drop 28 to 50 points. T-Mem drops 5.45. paper: https://t.co/JQAuX1dH4x code: https://t.co/YKFgFuRtIj (MIT)